Random projection-based partial feature extraction for robust face recognition

Chunfei Ma, June Young Jung, Seung Wook Kim, Sung-Jea Ko

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

In this paper, a novel feature extraction method for robust face recognition (FR) is proposed. The proposed method combines a simple yet effective dimensionality increasing (DI) method with an information-preserving dimensionality reduction (DR) method. For the proposed DI method, we employ the rectangle filters which sum the pixel values within a randomized rectangle window on the face image to extract the feature. By convolving the face image with all possible rectangle filters having various locations and scales, the face image in the image space is projected to a very high-dimensional feature space where more discriminative information can be incorporated. In order to significantly reduce the computational complexity while preserving the most informative features, we adopt a random projection method based on the compressed sensing theory for DR. Unlike the traditional holistic-based feature extraction methods requiring the time-consuming data-dependent training procedure, the proposed method has the partial-based and data-independent properties. Extensive experimental results on representative FR databases show that, as compared with conventional feature extraction methods, our proposed method not only achieves the higher recognition accuracy but also shows better robustness to corruption, occlusion, and disguise.

Original languageEnglish
Pages (from-to)1232-1244
Number of pages13
JournalNeurocomputing
Volume149
Issue numberPC
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

Face recognition
Feature extraction
Compressed sensing
Computational complexity
Pixels
Facial Recognition
Databases

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Cognitive Neuroscience

Cite this

Random projection-based partial feature extraction for robust face recognition. / Ma, Chunfei; Jung, June Young; Kim, Seung Wook; Ko, Sung-Jea.

In: Neurocomputing, Vol. 149, No. PC, 01.01.2015, p. 1232-1244.

Research output: Contribution to journalArticle

Ma, Chunfei ; Jung, June Young ; Kim, Seung Wook ; Ko, Sung-Jea. / Random projection-based partial feature extraction for robust face recognition. In: Neurocomputing. 2015 ; Vol. 149, No. PC. pp. 1232-1244.
@article{4a109e69cef64a03adbcdfa6d0fa319f,
title = "Random projection-based partial feature extraction for robust face recognition",
abstract = "In this paper, a novel feature extraction method for robust face recognition (FR) is proposed. The proposed method combines a simple yet effective dimensionality increasing (DI) method with an information-preserving dimensionality reduction (DR) method. For the proposed DI method, we employ the rectangle filters which sum the pixel values within a randomized rectangle window on the face image to extract the feature. By convolving the face image with all possible rectangle filters having various locations and scales, the face image in the image space is projected to a very high-dimensional feature space where more discriminative information can be incorporated. In order to significantly reduce the computational complexity while preserving the most informative features, we adopt a random projection method based on the compressed sensing theory for DR. Unlike the traditional holistic-based feature extraction methods requiring the time-consuming data-dependent training procedure, the proposed method has the partial-based and data-independent properties. Extensive experimental results on representative FR databases show that, as compared with conventional feature extraction methods, our proposed method not only achieves the higher recognition accuracy but also shows better robustness to corruption, occlusion, and disguise.",
keywords = "Compressed sensing, Face recognition, Feature extraction, Random projection, Robustness",
author = "Chunfei Ma and Jung, {June Young} and Kim, {Seung Wook} and Sung-Jea Ko",
year = "2015",
month = "1",
day = "1",
doi = "10.1016/j.neucom.2014.09.004",
language = "English",
volume = "149",
pages = "1232--1244",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "PC",

}

TY - JOUR

T1 - Random projection-based partial feature extraction for robust face recognition

AU - Ma, Chunfei

AU - Jung, June Young

AU - Kim, Seung Wook

AU - Ko, Sung-Jea

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In this paper, a novel feature extraction method for robust face recognition (FR) is proposed. The proposed method combines a simple yet effective dimensionality increasing (DI) method with an information-preserving dimensionality reduction (DR) method. For the proposed DI method, we employ the rectangle filters which sum the pixel values within a randomized rectangle window on the face image to extract the feature. By convolving the face image with all possible rectangle filters having various locations and scales, the face image in the image space is projected to a very high-dimensional feature space where more discriminative information can be incorporated. In order to significantly reduce the computational complexity while preserving the most informative features, we adopt a random projection method based on the compressed sensing theory for DR. Unlike the traditional holistic-based feature extraction methods requiring the time-consuming data-dependent training procedure, the proposed method has the partial-based and data-independent properties. Extensive experimental results on representative FR databases show that, as compared with conventional feature extraction methods, our proposed method not only achieves the higher recognition accuracy but also shows better robustness to corruption, occlusion, and disguise.

AB - In this paper, a novel feature extraction method for robust face recognition (FR) is proposed. The proposed method combines a simple yet effective dimensionality increasing (DI) method with an information-preserving dimensionality reduction (DR) method. For the proposed DI method, we employ the rectangle filters which sum the pixel values within a randomized rectangle window on the face image to extract the feature. By convolving the face image with all possible rectangle filters having various locations and scales, the face image in the image space is projected to a very high-dimensional feature space where more discriminative information can be incorporated. In order to significantly reduce the computational complexity while preserving the most informative features, we adopt a random projection method based on the compressed sensing theory for DR. Unlike the traditional holistic-based feature extraction methods requiring the time-consuming data-dependent training procedure, the proposed method has the partial-based and data-independent properties. Extensive experimental results on representative FR databases show that, as compared with conventional feature extraction methods, our proposed method not only achieves the higher recognition accuracy but also shows better robustness to corruption, occlusion, and disguise.

KW - Compressed sensing

KW - Face recognition

KW - Feature extraction

KW - Random projection

KW - Robustness

UR - http://www.scopus.com/inward/record.url?scp=84912531218&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84912531218&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2014.09.004

DO - 10.1016/j.neucom.2014.09.004

M3 - Article

VL - 149

SP - 1232

EP - 1244

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - PC

ER -